© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 42166
    Prev
    Next
    INDEX
    Explanations

    compare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inox
    -0.07
    controlled
    -0.07
    webpack
    -0.07
     Gotham
    -0.07
    setValue
    -0.07
    odore
    -0.07
    ochen
    -0.07
     Snow
    -0.07
    eği
    -0.07
    _ETH
    -0.07
    POSITIVE LOGITS
    שימוש
    0.07
    記事
    0.07
    '$
    0.07
    _used
    0.07
    apg
    0.06
     Disp
    0.06
    ,lat
    0.06
     Transitional
    0.06
     verification
    0.06
     ?>"/>↵
    0.06
    Activations Density 0.028%

    No Known Activations